PT  - JOURNAL ARTICLE
AU  - Joshua Meier
AU  - Roshan Rao
AU  - Robert Verkuil
AU  - Jason Liu
AU  - Tom Sercu
AU  - Alexander Rives
TI  - Language models enable zero-shot prediction of the effects of mutations on protein function
AID  - 10.1101/2021.07.09.450648
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.07.09.450648
4099  - http://biorxiv.org/content/early/2021/07/10/2021.07.09.450648.short
4100  - http://biorxiv.org/content/early/2021/07/10/2021.07.09.450648.full
AB  - Modeling the effect of sequence variation on function is a fundamental problem for understanding and designing proteins. Since evolution encodes information about function into patterns in protein sequences, unsupervised models of variant effects can be learned from sequence data. The approach to date has been to fit a model to a family of related sequences. The conventional setting is limited, since a new model must be trained for each prediction task. We show that using only zero-shot inference, without any supervision from experimental data or additional training, protein language models capture the functional effects of sequence variation, performing at state-of-the-art.Competing Interest StatementThe authors have declared no competing interest.